{"id":"W3150202690","doi":"10.48550/arxiv.2103.16617","title":"HAD-Net: A Hierarchical Adversarial Knowledge Distillation Network for Improved Enhanced Tumour Segmentation Without Post-Contrast Images","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Segmentation; Computer science; Artificial intelligence; Context (archaeology); Modality (human–computer interaction); Inference; Contrast (vision); Dice; Machine learning; Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008778417,0.001125167,0.0007309926,0.0004126907,0.000336403,0.0005260951,0.00158138,0.001424717,0.002524864],"category_scores_gemma":[0.002070699,0.000410925,0.000711476,0.0002675884,0.0008766305,0.001086179,0.001420327,0.001964983,0.0007574975],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008565468,"about_ca_system_score_gemma":0.0009973091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004852971,"about_ca_topic_score_gemma":0.006957816,"domain_scores_codex":[0.999711,0.00007502813,0.00001149949,0.00009681465,0.0000545999,0.00005107981],"domain_scores_gemma":[0.9994716,0.000295965,0.0000413049,0.00006668965,0.0000832314,0.00004117114],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004115216,0.0001520097,0.001133109,0.0001395203,0.0001140598,0.0002221814,0.0001057668,0.780792,0.00974152,0.007325783,0.00848205,0.1913805],"study_design_scores_gemma":[0.00001063445,0.00004816698,0.00009485687,0.000008827903,0.000009798707,0.00003043027,0.000006477427,0.9938623,0.002424414,0.002721559,0.0007758164,0.000006774936],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05562713,0.001256414,0.9295853,0.0009289148,0.000228013,0.0001158794,0.0004963704,0.005958234,0.005803763],"genre_scores_gemma":[0.778219,0.0004236212,0.2020405,0.001232272,0.0001094134,0.0001717672,0.001832879,0.0003536721,0.01561689],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004852971,"threshold_uncertainty_score":0.009649456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03022948599163722,"score_gpt":0.2225361786316715,"score_spread":0.1923066926400342,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}